CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts

—We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge of the properties of individual object classes, by solving a sequence of constrained parametric min-cut problems (CPMC) on a regular image grid. In a subsequent step, we learn to rank the corresponding segments by training a continuous model to predict how likely they are to exhibit real world regularities (expressed as putative overlap with ground truth) based on their mid-level region properties, then diversify the estimated overlap score using maximum marginal relevance measures. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC 2009 and 2010 datasets. In our companion papers [1], [2], we show that the algorit...

• Type: Journal
• Year: 2012
• Where: PAMI
• Authors: João Carreira, Cristian Sminchisescu
• Keywords: Companion Papers, Image Segmentation, PAMI 2012, Software Engineering, Spatial Extent